Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code keywords and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PYTHONPATH
    0.71
     PYTHON
    0.66
    pygame
    0.63
     Numpy
    0.62
    Python
    0.61
    numpy
    0.59
    PYTHON
    0.58
    python
    0.58
     Python
    0.58
     python
    0.57
    POSITIVE LOGITS
     !==
    1.47
     ===
    1.34
     `${
    1.19
    (`${
    1.16
    console
    1.13
    `${
    1.13
     eslint
    1.12
     undefined
    1.10
     console
    1.09
    undefined
    1.02
    Act Density 0.115%

    No Known Activations